A face hallucination method via HR-LLE coefficients constraint

Zhenli Wei, Xiaoguang Li, Li Zhuo

Abstract: In most of the existing LLE (Local Linear Embedding) based face hallucination methods, a LR (Low Resolution) face image is usually represented as a linear combination of training samples. The combination coefficients of LR image are then directly used to estimate the HR (High Resolution) image. However, due to the one-to-many mapping from LR to HR face space, the LR-LLE coefficients are not as the same as the corresponding HR-LLE coefficients. Therefore, the estimated HR faces are different from the ground truth. A novel face super-resolution(SR, also named face hallucination) method is proposed in this paper, in which a HR-LLE coefficients constraint is introduced to predict the coefficients of HR image. It can effectively reduce the error of the estimated HR-LLE coefficients. Then, we develop a novel method to perform face hallucination based on both the global and local features. Experimental results show that the proposed method provides improved performance over the compared methods in terms of both the subjective and objective quality.